Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.3287. Min Act: -0.1700
Data Index: 487579 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.1881. Min Act: -0.1700
Data Index: 75923 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0943. Min Act: -0.1700
Data Index: 289942 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0943. Min Act: -0.1700
Data Index: 140387 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0474. Min Act: -0.1700
Data Index: 950247 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0630. Min Act: -0.1700
Data Index: 418719 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0474. Min Act: -0.1700
Data Index: 1000012 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0474. Min Act: -0.1700
Data Index: 439525 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0318. Min Act: -0.1700
Data Index: 387349 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9849. Min Act: -0.1700
Data Index: 865874 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0318. Min Act: -0.1700
Data Index: 52478 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0005. Min Act: -0.1700
Data Index: 1138850 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9692. Min Act: -0.1700
Data Index: 550389 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0005. Min Act: -0.1700
Data Index: 1235855 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9536. Min Act: -0.1700
Data Index: 1123744 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3287. Min Range: -4.3287
Max Act: 4.0005. Min Act: -0.1700
Data Index: 946035 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9223. Min Act: -0.1700
Data Index: 1209977 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9223. Min Act: -0.1700
Data Index: 417952 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9223. Min Act: -0.1700
Data Index: 742760 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3287. Min Range: -4.3287
Max Act: 3.9223. Min Act: -0.1700
Data Index: 247004 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19